rumale 0.20.2 → 0.22.2

data/lib/rumale/linear_model/ridge.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::Ridge.new(reg_param: 0.1, max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::Ridge.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -70,7 +70,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      solver: 'auto',
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
@@ -85,7 +85,7 @@ module Rumale
         @params[:solver] = if solver == 'auto'
                              load_linalg? ? 'svd' : 'sgd'
                            else
-                             solver != 'svd' ? 'sgd' : 'svd'
+                             solver != 'svd' ? 'sgd' : 'svd' # rubocop:disable Style/NegatedIfElseCondition
                            end
         @params[:decay] ||= @params[:reg_param] * @params[:learning_rate]
         @params[:random_seed] ||= srand

data/lib/rumale/linear_model/svc.rb

@@ -11,13 +11,14 @@ module Rumale
     # with stochastic gradient descent optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
-    # Rumale::SVM provides linear support vector classifier based on LIBLINEAR.
-    # If you prefer execution speed, you should use Rumale::SVM::LinearSVC.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides linear support vector classifier based on LIBLINEAR.
+    #   If you prefer execution speed, you should use Rumale::SVM::LinearSVC.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::SVC.new(reg_param: 1.0, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::SVC.new(reg_param: 1.0, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_labels)
     #   results = estimator.predict(testing_samples)
     #
@@ -74,7 +75,7 @@ module Rumale
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      probability: false,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,

data/lib/rumale/linear_model/svr.rb

@@ -8,13 +8,14 @@ module Rumale
     # SVR is a class that implements Support Vector Regressor
     # with stochastic gradient descent optimization.
     #
-    # Rumale::SVM provides linear and kernel support vector regressor based on LIBLINEAR and LIBSVM.
-    # If you prefer execution speed, you should use Rumale::SVM::LinearSVR.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides linear and kernel support vector regressor based on LIBLINEAR and LIBSVM.
+    #   If you prefer execution speed, you should use Rumale::SVM::LinearSVR.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::SVR.new(reg_param: 1.0, epsilon: 0.1, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::SVR.new(reg_param: 1.0, epsilon: 0.1, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_target_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -68,7 +69,7 @@ module Rumale
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
                      epsilon: 0.1,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, bias_scale: bias_scale, epsilon: epsilon,

data/lib/rumale/metric_learning/mlkr.rb

@@ -0,0 +1,161 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/transformer'
+require 'rumale/decomposition/pca'
+require 'rumale/pairwise_metric'
+require 'rumale/utils'
+require 'lbfgsb'
+
+module Rumale
+  module MetricLearning
+    # MLKR is a class that implements Metric Learning for Kernel Regression.
+    #
+    # @example
+    #   transformer = Rumale::MetricLearning::MLKR.new
+    #   transformer.fit(training_samples, traininig_target_values)
+    #   low_samples = transformer.transform(testing_samples)
+    #
+    # *Reference*
+    # - Weinberger, K. Q. and Tesauro, G., "Metric Learning for Kernel Regression," Proc. AISTATS'07, pp. 612--629, 2007.
+    class MLKR
+      include Base::BaseEstimator
+      include Base::Transformer
+
+      # Returns the metric components.
+      # @return [Numo::DFloat] (shape: [n_components, n_features])
+      attr_reader :components
+
+      # Return the number of iterations run for optimization
+      # @return [Integer]
+      attr_reader :n_iter
+
+      # Return the random generator.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new transformer with MLKR.
+      #
+      # @param n_components [Integer] The number of components.
+      # @param init [String] The initialization method for components ('random' or 'pca').
+      # @param max_iter [Integer] The maximum number of iterations.
+      # @param tol [Float] The tolerance of termination criterion.
+      #   This value is given as tol / Lbfgsb::DBL_EPSILON to the factr argument of Lbfgsb.minimize method.
+      # @param verbose [Boolean] The flag indicating whether to output loss during iteration.
+      #   If true is given, 'iterate.dat' file is generated by lbfgsb.rb.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      def initialize(n_components: nil, init: 'random', max_iter: 100, tol: 1e-6, verbose: false, random_seed: nil)
+        check_params_numeric_or_nil(n_components: n_components, random_seed: random_seed)
+        check_params_numeric(max_iter: max_iter, tol: tol)
+        check_params_string(init: init)
+        check_params_boolean(verbose: verbose)
+        @params = {}
+        @params[:n_components] = n_components
+        @params[:init] = init
+        @params[:max_iter] = max_iter
+        @params[:tol] = tol
+        @params[:verbose] = verbose
+        @params[:random_seed] = random_seed
+        @params[:random_seed] ||= srand
+        @components = nil
+        @n_iter = nil
+        @rng = Random.new(@params[:random_seed])
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples]) The target values to be used for fitting the model.
+      # @return [MLKR] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+        n_features = x.shape[1]
+        n_components = if @params[:n_components].nil?
+                         n_features
+                       else
+                         [n_features, @params[:n_components]].min
+                       end
+        @components, @n_iter = optimize_components(x, y, n_features, n_components)
+        @prototypes = x.dot(@components.transpose)
+        @values = y
+        self
+      end
+
+      # Fit the model with training data, and then transform them with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples]) The target values to be used for fitting the model.
+      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data
+      def fit_transform(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+        fit(x, y).transform(x)
+      end
+
+      # Transform the given data with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The data to be transformed with the learned model.
+      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
+      def transform(x)
+        x = check_convert_sample_array(x)
+        x.dot(@components.transpose)
+      end
+
+      private
+
+      def init_components(x, n_features, n_components)
+        if @params[:init] == 'pca'
+          pca = Rumale::Decomposition::PCA.new(n_components: n_components)
+          pca.fit(x).components.flatten.dup
+        else
+          Rumale::Utils.rand_normal([n_features, n_components], @rng.dup).flatten.dup
+        end
+      end
+
+      def optimize_components(x, y, n_features, n_components)
+        # initialize components.
+        comp_init = init_components(x, n_features, n_components)
+        # initialize optimization results.
+        res = {}
+        res[:x] = comp_init
+        res[:n_iter] = 0
+        # perform optimization.
+        verbose = @params[:verbose] ? 1 : -1
+        res = Lbfgsb.minimize(
+          fnc: method(:mlkr_fnc), jcb: true, x_init: comp_init, args: [x, y],
+          maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
+        )
+        # return the results.
+        n_iter = res[:n_iter]
+        comps = n_components == 1 ? res[:x].dup : res[:x].reshape(n_components, n_features)
+        [comps, n_iter]
+      end
+
+      def mlkr_fnc(w, x, y)
+        # initialize some variables.
+        n_features = x.shape[1]
+        n_components = w.size / n_features
+        # projection.
+        w = w.reshape(n_components, n_features)
+        z = x.dot(w.transpose)
+        # predict values.
+        kernel_mat = Numo::NMath.exp(-Rumale::PairwiseMetric.squared_error(z))
+        kernel_mat[kernel_mat.diag_indices] = 0.0
+        norm = kernel_mat.sum(1)
+        norm[norm.eq(0)] = 1
+        y_pred = kernel_mat.dot(y) / norm
+        # calculate loss.
+        y_diff = y_pred - y
+        loss = (y_diff**2).sum
+        # calculate gradient.
+        weight_mat = y_diff * y_diff.expand_dims(1) * kernel_mat
+        weight_mat = weight_mat.sum(0).diag - weight_mat
+        gradient = 8 * z.transpose.dot(weight_mat).dot(x)
+        [loss, gradient.flatten.dup]
+      end
+    end
+  end
+end

data/lib/rumale/metric_learning/neighbourhood_component_analysis.rb

@@ -2,13 +2,15 @@
 
 require 'rumale/base/base_estimator'
 require 'rumale/base/transformer'
+require 'rumale/utils'
+require 'rumale/pairwise_metric'
+require 'lbfgsb'
 
 module Rumale
   module MetricLearning
     # NeighbourhoodComponentAnalysis is a class that implements Neighbourhood Component Analysis.
     #
     # @example
-    #   require 'mopti'
     #   require 'rumale'
     #
     #   transformer = Rumale::MetricLearning::NeighbourhoodComponentAnalysis.new
@@ -39,7 +41,9 @@ module Rumale
       # @param init [String] The initialization method for components ('random' or 'pca').
       # @param max_iter [Integer] The maximum number of iterations.
       # @param tol [Float] The tolerance of termination criterion.
+      #   This value is given as tol / Lbfgsb::DBL_EPSILON to the factr argument of Lbfgsb.minimize method.
       # @param verbose [Boolean] The flag indicating whether to output loss during iteration.
+      #   If true is given, 'iterate.dat' file is generated by lbfgsb.rb.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(n_components: nil, init: 'random', max_iter: 100, tol: 1e-6, verbose: false, random_seed: nil)
         check_params_numeric_or_nil(n_components: n_components, random_seed: random_seed)
@@ -65,8 +69,6 @@ module Rumale
       # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
       # @return [NeighbourhoodComponentAnalysis] The learned classifier itself.
       def fit(x, y)
-        raise 'NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded.' unless enable_mopti?
-
         x = check_convert_sample_array(x)
         y = check_convert_label_array(y)
         check_sample_label_size(x, y)
@@ -102,17 +104,9 @@ module Rumale
 
       private
 
-      def enable_mopti?
-        if defined?(Mopti).nil?
-          warn('NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded. You should intall and load mopti gem in advance.')
-          return false
-        end
-        true
-      end
-
       def init_components(x, n_features, n_components)
         if @params[:init] == 'pca'
-          pca = Rumale::Decomposition::PCA.new(n_components: n_components, solver: 'evd')
+          pca = Rumale::Decomposition::PCA.new(n_components: n_components)
           pca.fit(x).components.flatten.dup
         else
           Rumale::Utils.rand_normal([n_features, n_components], @rng.dup).flatten.dup
@@ -127,28 +121,18 @@ module Rumale
         res[:x] = comp_init
         res[:n_iter] = 0
         # perform optimization.
-        optimizer = Mopti::ScaledConjugateGradient.new(
-          fnc: method(:nca_loss), jcb: method(:nca_dloss),
-          x_init: comp_init, args: [x, y],
-          max_iter: @params[:max_iter], ftol: @params[:tol]
+        verbose = @params[:verbose] ? 1 : -1
+        res = Lbfgsb.minimize(
+          fnc: method(:nca_fnc), jcb: true, x_init: comp_init, args: [x, y],
+          maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
         )
-        fold = 0.0
-        dold = 0.0
-        optimizer.each do |prm|
-          res = prm
-          puts "[NeighbourhoodComponentAnalysis] The value of objective function after #{res[:n_iter]} epochs: #{x.shape[0] - res[:fnc]}" if @params[:verbose]
-          break if (fold - res[:fnc]).abs <= @params[:tol] && (dold - res[:jcb]).abs <= @params[:tol]
-
-          fold = res[:fnc]
-          dold = res[:jcb]
-        end
         # return the results.
         n_iter = res[:n_iter]
         comps = n_components == 1 ? res[:x].dup : res[:x].reshape(n_components, n_features)
         [comps, n_iter]
       end
 
-      def nca_loss(w, x, y)
+      def nca_fnc(w, x, y)
         # initialize some variables.
         n_samples, n_features = x.shape
         n_components = w.size / n_features
@@ -157,32 +141,19 @@ module Rumale
         z = x.dot(w.transpose)
         # calculate probability matrix.
         prob_mat = probability_matrix(z)
-        # calculate loss.
+        # calculate loss and gradient.
         # NOTE:
         # NCA attempts to maximize its objective function.
         # For the minization algorithm, the objective function value is subtracted from the maixmum value (n_samples).
         mask_mat = y.expand_dims(1).eq(y)
         masked_prob_mat = prob_mat * mask_mat
-        n_samples - masked_prob_mat.sum
-      end
-
-      def nca_dloss(w, x, y)
-        # initialize some variables.
-        n_features = x.shape[1]
-        n_components = w.size / n_features
-        # projection.
-        w = w.reshape(n_components, n_features)
-        z = x.dot(w.transpose)
-        # calculate probability matrix.
-        prob_mat = probability_matrix(z)
-        # calculate gradient.
-        mask_mat = y.expand_dims(1).eq(y)
-        masked_prob_mat = prob_mat * mask_mat
-        weighted_prob_mat = masked_prob_mat - prob_mat * masked_prob_mat.sum(1).expand_dims(1)
-        weighted_prob_mat += weighted_prob_mat.transpose
-        weighted_prob_mat[weighted_prob_mat.diag_indices] = -weighted_prob_mat.sum(0)
-        gradient = 2 * z.transpose.dot(weighted_prob_mat).dot(x)
-        -gradient.flatten.dup
+        loss = n_samples - masked_prob_mat.sum
+        sum_probs = masked_prob_mat.sum(1)
+        weight_mat = (sum_probs.expand_dims(1) * prob_mat - masked_prob_mat)
+        weight_mat += weight_mat.transpose
+        weight_mat = weight_mat.sum(0).diag - weight_mat
+        gradient = -2 * z.transpose.dot(weight_mat).dot(x)
+        [loss, gradient.flatten.dup]
       end
 
       def probability_matrix(z)

data/lib/rumale/pairwise_metric.rb

@@ -123,7 +123,7 @@ module Rumale
       # @param gamma [Float] The parameter of polynomial kernel, if nil it is 1 / n_features.
       # @param coef [Integer] The parameter of polynomial kernel.
       # @return [Numo::DFloat] (shape: [n_samples_x, n_samples_x] or [n_samples_x, n_samples_y] if y is given)
-      def polynomial_kernel(x, y = nil, degree = 3, gamma = nil, coef = 1)
+      def polynomial_kernel(x, y = nil, degree = 3, gamma = nil, coef = 1) # rubocop:disable Metrics/ParameterLists
         y = x if y.nil?
         gamma ||= 1.0 / x.shape[1]
         x = Rumale::Validation.check_convert_sample_array(x)

data/lib/rumale/pipeline/pipeline.rb

@@ -140,7 +140,7 @@ module Rumale
       def validate_steps(steps)
         steps.keys[0...-1].each do |name|
           transformer = steps[name]
-          next if transformer.nil? || %i[fit transform].all? { |m| transformer.class.method_defined?(m) }
+          next if transformer.nil? || (transformer.class.method_defined?(:fit) && transformer.class.method_defined?(:transform))
 
           raise TypeError,
                 'Class of intermediate step in pipeline should be implemented fit and transform methods: ' \

data/lib/rumale/tree/base_decision_tree.rb

@@ -75,17 +75,10 @@ module Rumale
         node = Node.new(depth: depth, impurity: impurity, n_samples: n_samples)
 
         # terminate growing.
-        unless @params[:max_leaf_nodes].nil?
-          return nil if @n_leaves >= @params[:max_leaf_nodes]
-        end
-
+        return nil if !@params[:max_leaf_nodes].nil? && @n_leaves >= @params[:max_leaf_nodes]
         return nil if n_samples < @params[:min_samples_leaf]
         return put_leaf(node, y) if n_samples == @params[:min_samples_leaf]
-
-        unless @params[:max_depth].nil?
-          return put_leaf(node, y) if depth == @params[:max_depth]
-        end
-
+        return put_leaf(node, y) if !@params[:max_depth].nil? && depth == @params[:max_depth]
         return put_leaf(node, y) if stop_growing?(y)
 
         # calculate optimal parameters.

data/lib/rumale/tree/gradient_tree_regressor.rb

@@ -138,7 +138,7 @@ module Rumale
         nil
       end
 
-      def grow_node(depth, x, y, g, h)
+      def grow_node(depth, x, y, g, h) # rubocop:disable Metrics/AbcSize
         # intialize some variables.
         sum_g = g.sum
         sum_h = h.sum
@@ -146,17 +146,10 @@ module Rumale
         node = Node.new(depth: depth, n_samples: n_samples)
 
         # terminate growing.
-        unless @params[:max_leaf_nodes].nil?
-          return nil if @n_leaves >= @params[:max_leaf_nodes]
-        end
-
+        return nil if !@params[:max_leaf_nodes].nil? && @n_leaves >= @params[:max_leaf_nodes]
         return nil if n_samples < @params[:min_samples_leaf]
         return put_leaf(node, sum_g, sum_h) if n_samples == @params[:min_samples_leaf]
-
-        unless @params[:max_depth].nil?
-          return put_leaf(node, sum_g, sum_h) if depth == @params[:max_depth]
-        end
-
+        return put_leaf(node, sum_g, sum_h) if !@params[:max_depth].nil? && depth == @params[:max_depth]
         return put_leaf(node, sum_g, sum_h) if stop_growing?(y)
 
         # calculate optimal parameters.

data/lib/rumale/validation.rb

@@ -109,7 +109,7 @@ module Rumale
 
     # @!visibility private
     def check_params_positive(params = {})
-      params.reject { |_, v| v.nil? }.each { |k, v| raise ArgumentError, "Expect #{k} to be positive value" if v.negative? }
+      params.compact.each { |k, v| raise ArgumentError, "Expect #{k} to be positive value" if v.negative? }
       nil
     end
   end